From e6bd5cf68a35c9b693e1c9623a8f1cdc9244cbca Mon Sep 17 00:00:00 2001 From: Eben Olson Date: Sat, 29 Aug 2015 09:35:26 -0400 Subject: [PATCH] Update README.md --- examples/imagecaption/README.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/examples/imagecaption/README.md b/examples/imagecaption/README.md index 9bf608a..6252016 100644 --- a/examples/imagecaption/README.md +++ b/examples/imagecaption/README.md @@ -3,6 +3,7 @@ This is a partial implementation of "Show and Tell: A Neural Image Caption Generator" (http://arxiv.org/abs/1411.4555), borrowing heavily from Andrej Karpathy's NeuralTalk (https://github.com/karpathy/neuraltalk) This example consists of three parts: + 1. COCO Preprocessing - prepare the dataset by precomputing image representations using GoogLeNet 2. RNN Training - train a network to predict image captions -3. Caption Generation - use the trained network to caption new images \ No newline at end of file +3. Caption Generation - use the trained network to caption new images